DocumentCode :
672620
Title :
Anisotropic diffusion based edge detector for detecting coral reefs edges
Author :
Awalludin, Ezmahamrul Afreen ; Hitam, M.S. ; Bachok, Z. ; Wan Yussof, Wan Nural Jawahir Hj ; Muslim, Aidy Mohamed Shawal M.
Author_Institution :
Inst. of Oceanogr. & Environ. (INOS), Univ. Malaysia Terengganu (UMT), Kuala Terengganu, Malaysia
fYear :
2013
fDate :
8-10 Oct. 2013
Firstpage :
226
Lastpage :
231
Abstract :
This paper presents a new edge detection method to efficiently detect coral reefs edges. The new edge detection method is based on an anisotropic diffusion where it is used to produce minimum image noise disturbances without reducing the significant edge information and at the same time preserving salient edges. The proposed method has been compared with other established edge detection methods such as Sobel, Prewitt, Roberts, LoG and Canny edge detectors under various noisy environments. The coral reefs images obtained at 3 meters depth were used in this study. The performance of the proposed method is compared with other established methods using visual inspection as well as parametric measure, i.e. Mean Square Error (MSE) and Peak Signal-to-Noise Ratio (PSNR). The experimental results show that the proposed method outperformed other established edge detection methods in both aspects.
Keywords :
computer vision; edge detection; mean square error methods; oceanographic techniques; MSE; PSNR; anisotropic diffusion; coral reef edges; edge detection method; image noise disturbance; mean square error; parametric measure; peak signal-to-noise ratio; salient edges; visual inspection; Anisotropic magnetoresistance; Conferences; Detectors; Gaussian noise; Image edge detection; PSNR;
fLanguage :
English
Publisher :
ieee
Conference_Titel :
Signal and Image Processing Applications (ICSIPA), 2013 IEEE International Conference on
Conference_Location :
Melaka
Print_ISBN :
978-1-4799-0267-5
Type :
conf
DOI :
10.1109/ICSIPA.2013.6708008
Filename :
6708008
Link To Document :
بازگشت